High-throughput event streaming and real-time data ingestion.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow consumes events from Azure Event Hubs where external publishers can submit arbitrary messages, representing an monitored input queue.
popey/claude-code-skills
a5a6601
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.